Exercício 12
Dependências
install.packages("dplyr")
## Installing package into '/home/lucas.burle/R/x86_64-pc-linux-gnu-library/4.1'
## (as 'lib' is unspecified)
library("dplyr")
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
install.packages("tidyr")
## Installing package into '/home/lucas.burle/R/x86_64-pc-linux-gnu-library/4.1'
## (as 'lib' is unspecified)
library("tidyr")
install.packages("plotly")
## Installing package into '/home/lucas.burle/R/x86_64-pc-linux-gnu-library/4.1'
## (as 'lib' is unspecified)
library("plotly")
## Carregando pacotes exigidos: ggplot2
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
Questão 1
MRT_1F <-c(517.1468515630205, 85.13094142168089, 30.333207896694553, 12.694776264558937, 3.3041601673945418, 1.1823111717498882, 1.1892293502386786)
MRT_3F <-c(156.68929936163462, 11.540837783562276, 0.4512835621696538, 0.4509797929766453, 0.4502068233039181, 0.4496185276300172, 0.4543157082191288)
MRT_5F <-c(83.90319666471157, 0.3068151086494968, 0.30522314133037304, 0.3072588968084928, 0.30655265997285697, 0.3055812715727718, 0.3053297166713006)
MRT_10F <-c(29.55430642951759, 0.19832832665772515, 0.1971923924717474, 0.19796648905716516, 0.19615594370806338, 0.2034569237883263, 0.19617420889447737)
MRT_15F <-c(11.317736530583566, 0.167364215666193, 0.16172168266811013, 0.16701085329580515, 0.1598052657153692, 0.1645934043532696, 0.16216563797118075)
MRT_sem_F <-c(11.93430909937736, 0.6095414637034009, 0.6060645101029295, 0.612167181646899, 0.6146761002685637, 0.6096747087200697, 0.6125810476877268)
clock <- c(0.1, 0.5, 1, 1.5, 2, 2.5, 3)
xlim <- max(clock)
ylim <- max(c(MRT_1F, MRT_3F, MRT_5F, MRT_10F, MRT_15F, MRT_sem_F))
plot(clock, MRT_1F, type="o", col="black", pch=4,
xlim=c(0, xlim), ylim=c(0, ylim),
ylab="Response Time (sec.)",
xlab="Time between Things requests (seconds)")
lines(clock, MRT_3F, type="o", col="yellow", pch=11)
lines(clock, MRT_5F, type="o", col="red", pch=1)
lines(clock, MRT_10F, type="o", col="blue", pch=2)
lines(clock, MRT_15F, type="o", col="purple", pch=5)
lines(clock, MRT_sem_F, type="o", col="green", pch=4)
legend("topright", pch=c(4, 11, 1, 2, 5, 4),
col=c("black", "yellow", "red", "blue", "purple", "green"),
legend=c("1 Fog", "3 Fogs", "5 Fogs", "10 Fogs", "15 Fogs", "w/o Fog"))
layout(matrix(c(1, 2,
3, 4,
5, 0), nrow=3, byrow=TRUE))
barplot(rbind(MRT_sem_F, MRT_1F),
names.arg=clock,
log="y",
col=c("#E6E6E6", "#666666"),
beside=T,
xlab="Time between Things requests",
ylab="Response Time (s)")
legend("topright", pch=c(15, 15),
col=c("#E6E6E6", "#666666"),
legend=c("w/o Fogs", "1 Fog"))
barplot(rbind(MRT_sem_F, MRT_3F),
names.arg=clock,
log="y",
col=c("#E6E6E6", "#666666"),
beside=T,
xlab="Time between Things requests",
ylab="Response Time (s)")
legend("topright", pch=c(15, 15),
col=c("#E6E6E6", "#666666"),
legend=c("w/o Fogs", "3 Fogs"))
barplot(rbind(MRT_sem_F, MRT_5F),
names.arg=clock,
log="y",
col=c("#E6E6E6", "#666666"),
beside=T,
xlab="Time between Things requests",
ylab="Response Time (s)")
legend("topright", pch=c(15, 15),
col=c("#E6E6E6", "#666666"),
legend=c("w/o Fogs", "5 Fogs"))
barplot(rbind(MRT_sem_F, MRT_10F),
names.arg=clock,
log="y",
col=c("#E6E6E6", "#666666"),
beside=T,
xlab="Time between Things requests",
ylab="Response Time (s)")
legend("topright", pch=c(15, 15),
col=c("#E6E6E6", "#666666"),
legend=c("w/o Fogs", "10 Fogs"))
barplot(rbind(MRT_sem_F, MRT_15F),
names.arg=clock,
log="y",
col=c("#E6E6E6", "#666666"),
beside=T,
xlab="Time between Things requests",
ylab="Response Time (s)")
legend("topright", pch=c(15, 15),
col=c("#E6E6E6", "#666666"),
legend=c("w/o Fogs", "15 Fogs"))
Questão 2
good <- c(53.8, 33.9, 2.6, 0)
very_good <- c(43.6, 54.2, 60.5, 21.4)
excellent <- c(2.6, 11.9, 36.8, 78.6)
bardata <- rbind(good, very_good, excellent)
labels <- c("$10-19", "$20-29", "$30-39", "$40-49")
barplot(bardata,
names.arg=labels,
main="Meal",
ylab="Quality Rating",
xlab="Meal Price",
xlim=c(0, 8),
space=0.5,
col=rainbow(3))
legend("topright",
col=rainbow(3),
lwd=10,
legend=c("Good", "Very Good", "Excellent"))
Questão 3
temp <- airquality %>%
filter((Month == 5)) %>%
select(Temp)
temp <- (temp - 32) / 1.8
hist(temp$Temp,
main="Temperatura em Maio",
xlab="Temperatura",
ylab="Frequência",
probability = T,
col=c(2:9))
lines(density(temp$Temp))
Questão 4
sales <- read.table("https://training-course-material.com/images/8/8f/Sales.txt",header=TRUE)
pie(sales$SALES,
labels = paste(round((sales$SALES/sum(sales$SALES))*100, 2), rep("%", length(sales$COUNTRY)), sep = ""),
col=rainbow(length(sales$COUNTRY)),
main="Sales By Country")
legend("topright",
fill = rainbow(length(sales$COUNTRY)),
legend=sales$COUNTRY)
Questão 5
boxplot(InsectSprays$count ~ InsectSprays$spray,
main="Insect Sprays",
ylab="Insect Count",
xlab="Spray Category",
col="yellow",
)
Questão 6
monitoring01 <- read.csv("monitoringCloudData/monitoringCloudData_0.1.csv")
monitoring05 <- read.csv("monitoringCloudData/monitoringCloudData_0.5.csv")
monitoring1 <- read.csv("monitoringCloudData/monitoringCloudData_1.csv")
monitoringnone <- read.csv("monitoringCloudData/monitoringCloudData_NONE.csv")
# Convertendo currentTime para DataTime
monitoring01$currentTime <- as.POSIXct(monitoring01$currentTime, format="%Y-%m-%d %H:%M:%S", tz="UTC")
monitoring05$currentTime <- as.POSIXct(monitoring05$currentTime, format="%Y-%m-%d %H:%M:%S", tz="UTC")
monitoring1$currentTime <- as.POSIXct(monitoring1$currentTime, format="%Y-%m-%d %H:%M:%S", tz="UTC")
monitoringnone$currentTime <- as.POSIXct(monitoringnone$currentTime, format="%Y-%m-%d %H:%M:%S", tz="UTC")
# Ordenando de forma descendente por currentTime
monitoring01 <- monitoring01[order(monitoring01$currentTime), ]
monitoring05 <- monitoring05[order(monitoring05$currentTime), ]
monitoring1 <- monitoring1[order(monitoring1$currentTime), ]
monitoringnone <- monitoringnone[order(monitoringnone$currentTime), ]
# Com currentTime ordenado é possível converter a coluna para valores unitários de hora
# realizando a operação (hora_atual - primeira_hora)
monitoring01$currentTime <- difftime(monitoring01$currentTime, monitoring01[1,"currentTime"], units = "hours")
monitoring05$currentTime <- difftime(monitoring05$currentTime, monitoring05[1,"currentTime"], units = "hours")
monitoring1$currentTime <- difftime(monitoring1$currentTime, monitoring1[1,"currentTime"], units = "hours")
monitoringnone$currentTime <- difftime(monitoringnone$currentTime, monitoringnone[1,"currentTime"], units = "hours")
# Separando usedMemory em duas colunas usedMemory e usedMemoryUnit.
# usedMemory contêm a quantidade de memória utilizada.
# usedMemoryUnit contém a unidade da quantidade de memória utilizada. Por exemplo "GB", "MB", "TB".
monitoring01 <- monitoring01 %>% extract(usedMemory, into=c("usedMemory", "usedMemoryUnit"), regex="([[:digit:].]+)(PB|TB|GB|MB|KB)")
monitoring05 <- monitoring05 %>% extract(usedMemory, into=c("usedMemory", "usedMemoryUnit"), regex="([[:digit:].]+)(PB|TB|GB|MB|KB)")
monitoring1 <- monitoring1 %>% extract(usedMemory, into=c("usedMemory", "usedMemoryUnit"), regex="([[:digit:].]+)(PB|TB|GB|MB|KB)")
monitoringnone <- monitoringnone %>% extract(usedMemory, into=c("usedMemory", "usedMemoryUnit"), regex="([[:digit:].]+)(PB|TB|GB|MB|KB)")
convert_to_mb <- function(df) {
unit <- df[6]
value <- as.numeric(df[5])
switch(unit,
"MB" = value,
"GB" = value * 1024,
"TB" = value * 1000000,
stop("Unknown unit: ", unit))
}
plot(monitoring01$currentTime, apply(monitoring01, 1, convert_to_mb), type="l")
layout(matrix(c(1, 2,
3, 4), nrow=2, byrow=TRUE))
plot(monitoringnone$currentTime, apply(monitoringnone, 1, convert_to_mb),
type="l",
xlab="Time (hour)",
ylab="Used Memory (MB)",
main="Memory Analysis (None Workload)")
plot(monitoring01$currentTime, apply(monitoring01, 1, convert_to_mb), type="l",
xlab="Time (hour)",
ylab="Used Memory (MB)",
main="Memory Analysis (Workload of 0.1)")
plot(monitoring05$currentTime, apply(monitoring05, 1, convert_to_mb), type="l",
xlab="Time (hour)",
ylab="Used Memory (MB)",
main="Memory Analysis (Workload of 0.5)")
plot(monitoring1$currentTime, apply(monitoring1, 1, convert_to_mb), type="l",
xlab="Time (hour)",
ylab="Used Memory (MB)",
main="Memory Analysis (Workload of 1.0)")
Questão 7
df <- read.csv("netflix_titles.csv", na.strings = "")
top_10 <- df %>%
filter(!is.na(country)) %>%
count(country, sort=T) %>%
top_n(10)
## Selecting by n
fig <- plot_ly(top_10, labels=top_10$country, values=top_10$n, type="pie")
fig
Questão 8
df <- read.csv("netflix_titles.csv", na.strings = "")
top_10 <- df %>%
filter(!is.na(country)) %>%
count(country, sort=T) %>%
top_n(10)
## Selecting by n
fig <- plot_ly(type="table",
header = list(
values = c("País", "Total de conteúdos"),
align = c("center", "center"),
fill = list(color = c("grey", "grey")),
font = list(color = "white")
),
cells =list(
values = rbind(top_10$country, top_10$n),
align = c("center", "center")
))
fig
Questão 9
df <- read.csv("netflix_titles.csv", na.strings = "")
df$type <- factor(df$type)
movies <- df %>%
filter(type == "Movie") %>%
select(release_year) %>%
mutate(release_year = release_year - release_year %% 10) %>%
rename("decade" = "release_year") %>%
count(decade)
tv_shows <- df %>%
filter(type == "TV Show") %>%
select(release_year) %>%
mutate(release_year = release_year - release_year %% 10) %>%
rename("decade" = "release_year") %>%
count(decade)
fig <- plot_ly(movies, x = movies$decade, y = movies$n, type="scatter", name="Movies", mode = "lines+markers")
fig <- fig %>% add_trace(y = tv_shows$n, name="TV Shows", mode = "lines+markers")
fig
Questão 10
df <- read.csv("netflix_titles.csv", na.strings = "")
df <- df %>%
filter(release_year >= 2000 & release_year <= 2010) %>%
select(release_year, listed_in) %>%
separate(listed_in, c("gender"), sep = ",", remove = T, extra="drop") %>%
filter(gender %in% c("Dramas", "Action & Adventure", "Comedies")) %>%
group_by(release_year, gender) %>%
count()
dramas <- df %>% filter(gender == "Dramas")
actionAdventure <- df %>% filter(gender == "Action & Adventure")
comedies <- df %>% filter(gender == "Comedies")
fig <- plot_ly(df, x = dramas$release_year, y = dramas$n, name="Dramas", type = "bar")
fig <- fig %>% add_trace(y = actionAdventure$n, name = "Ação e Aventura")
fig <- fig %>% add_trace(y = comedies$n, name="Comédia")
fig